find-new-resources

Find new Japanese NLP GitHub repositories and Hugging Face models/datasets for topic: "$ARGUMENTS" that are not already in the awesome-japanese-nlp-resources list.

Instructions

Preamble — Establish the current date

Before doing anything else, run this once and remember the values — every step that mentions a year refers to them:

echo "YEAR_NOW=$(date +%Y)"
echo "YEAR_PREV=$(($(date +%Y) - 1))"

Substitute these everywhere this skill writes ${YEAR_NOW} or ${YEAR_PREV} below. Do not hardcode years — the skill must always reflect the current year.

Step 0 — Handle empty input

If $ARGUMENTS is empty or blank, treat it as a general search for the latest Japanese NLP resources. Use the following default settings for the rest of the steps:

• Topic label for output headings: "Latest Japanese NLP Resources" (use "最新の日本語NLPリソース" only when the user's query was written in Japanese)
• Keywords for Step 1: japanese nlp, 日本語 nlp, japanese language processing, japanese machine learning
• WebSearch queries for Step 4: focus on recency — add ${YEAR_PREV} ${YEAR_NOW} to every query, and include:
  • japanese NLP new library github ${YEAR_NOW}
  • 日本語 NLP 新しい ライブラリ github ${YEAR_NOW}
  • awesome japanese nlp ${YEAR_PREV} ${YEAR_NOW} new
  • japanese natural language processing tool released ${YEAR_PREV} ${YEAR_NOW}
  • japanese NLP new model huggingface ${YEAR_NOW}
  • huggingface japanese nlp ${YEAR_PREV} ${YEAR_NOW} new
• Output heading: "New Japanese NLP Resource Candidates" instead of New candidates for "$ARGUMENTS" (use "最近追加された日本語NLPリソース候補" only when the output language is Japanese)

Then continue normally from Step 1 using the above defaults.

Step 1 — Interpret the topic

The user's topic is: "$ARGUMENTS"

Translate the topic intent to English keywords for search. Aim for 3–5 keywords/phrases. Use the same stem + tool-name conventions as the search skill:

Domain (Japanese hint)	English keywords / search phrases
形態素解析 / morphological analysis	japanese morphological analyzer, japanese tokenizer, mecab, sudachi, janome
固有表現認識 / NER	japanese named entity recognition, japanese NER, ginza
係り受け解析 / dependency parsing	japanese dependency parser, cabocha, knp
文章分類 / text classification	japanese text classification, japanese sentiment
埋め込み / embeddings	japanese sentence embedding, japanese embedding model, ruri, sbert
事前学習モデル / pretrained model	japanese pretrained model, japanese LLM, japanese BERT, japanese GPT
LLM / 大規模言語モデル	japanese llm, japanese language model, llama japanese, swallow, elyza
テキスト生成 / generation	japanese text generation, japanese chatbot
機械翻訳 / translation	japanese machine translation, english japanese translation
音声認識 / speech	japanese speech recognition, japanese asr, whisper japanese
音声合成 / TTS	japanese text to speech, japanese tts, voicevox
質問応答 / QA	japanese question answering, japanese qa dataset
要約 / summarization	japanese summarization, japanese abstractive summarization
辞書 / dictionary・IME	japanese dictionary, japanese ime, mozc
コーパス / corpus	japanese corpus, japanese dataset, japanese annotated
OCR	japanese ocr, manga ocr
RAG	japanese rag, japanese retrieval, japanese reranker
ファインチューニング	japanese fine-tuning, japanese lora, japanese instruction tuning
ベンチマーク / 評価	japanese benchmark, japanese evaluation, jglue, llm-jp-eval